Papers › Data Models for Dataset Drift Controls in Machine Learning With Optical Images

Data Models for Dataset Drift Controls in Machine Learning With Optical Images

4 Nov 2022arXiv:2211.02578archive 2025-07-28

Luis Oala, Marco Aversa, Gabriel Nobis, Kurt Willis, Yoan Neuenschwander, Michèle Buck, Christian Matek, Jerome Extermann, Enrico Pomarico, Wojciech Samek, Roderick Murray-Smith, Christoph Clausen, Bruno Sanguinetti

Camera images are ubiquitous in machine learning research. They also play a central role in the delivery of important services spanning medicine and environmental surveying. However, the application of machine learning models in these domains has been limited because of robustness concerns. A primary failure mode are performance drops due to differences between the training and deployment data. While there are methods to prospectively validate the robustness of machine learning models to such dataset drifts, existing approaches do not account for explicit models of the primary object of interest: the data. This limits our ability to study and understand the relationship between data generation and downstream machine learning model performance in a physically accurate manner. In this study, we demonstrate how to overcome this limitation by pairing traditional machine learning with physical optics to obtain explicit and differentiable data models. We demonstrate how such data models can be constructed for image data and used to control downstream machine learning model performance related to dataset drift. The findings are distilled into three applications. First, drift synthesis enables the controlled generation of physically faithful drift test cases to power model selection and targeted generalization. Second, the gradient connection between machine learning task model and data model allows advanced, precise tolerancing of task model sensitivity to changes in the data generation. These drift forensics can be used to precisely specify the acceptable data environments in which a task model may be run. Third, drift optimization opens up the possibility to create drifts that can help the task model learn better faster, effectively optimizing the data generating process itself. A guide to access the open code and datasets is available at https://github.com/aiaudit-org/raw2logit.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 18 code samples harvested from 1 repository linked to this paper: 17 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 3 honoured, 0 violated, 12 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 18 samples from 1 repository, 17 ran (15 with no instrument failure; 2 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 2 of the 17 samples that ran have no recorded date.

aiaudit-org/raw2logit officialmentioned in papermentioned on GitHubpytorchMITSyntology: 18 samples, 17 ran (2 instrument-failed) · 1 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

18 samples harvested: 17 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 3 honoured, 0 violated, 12 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

3ran · honoured contract
2ran · our draft was wrong
12ran
1unverified

Licence: 0 of the 18 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from aiaudit-org/raw2logit. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. For 1 sample that ran, the graph records a signature this page does not show: an argument's recorded type or element kind is a printout of an object in Syntology's harness (such as a mock object, a class or a pandas printout), not the type of an input, so it does not describe the call's shape. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

aiaudit-org/raw2logit official repository 18 samples, 17 ran (2 instrument-failed) · 1 unverified
clipped_zoom in 13 papers
census: 4 implementations from 8 papers, 3 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 3, kind float, dtype float32
utils/hendrycks_robustness.py ran · our draft was wrong fingerprinted MIT (permissive) · 466ca3cdf4524d82 · report fixture: signature img:ndarray/3/float, zoom_factor:float/0/float · returned ndarray · level recorded, date not recorded
create_window in 82 papers utils/ssim.py ran · honoured contract fingerprinted MIT (permissive) · 6154e3744ece5728 · report fixture: signature window_size:int/0/int, channel:int/0/int · returned Tensor · level recorded 2026-09-22
disk in 8 papers utils/hendrycks_robustness.py ran · honoured contract MIT (permissive) · bc8b7f1d3348c560 · report fixture: returned ndarray · level recorded 2026-09-24
gaussian in 218 papers
census: 8 implementations from 9 papers, 8 distinct outputs across 4 buckets, one shared input per bucket
utils/ssim.py ran · honoured contract fingerprinted MIT (permissive) · c56b7ef16f309a45 · report fixture: signature window_size:int/0/int, sigma:float/0/float · returned Tensor · level recorded, date not recorded
get_augmentation in 19 papers utils/augmentation.py ran MIT (permissive) · 8c45fb3e0cb23785 · report fixture: signature type:str/0/str · returned ComposeState · level recorded 2026-09-25
get_camera_parameters processing/pipeline_numpy.py ran MIT (permissive) · 1b7982e1820dcf5c · report fixture: signature rawpyImg:MockRawPyImage/0/? · returned tuple · level recorded 2026-09-25
k_fold in 9 papers utils/dataset_utils.py ran MIT (permissive) · 9c5e093b8d866226 · report fixture: signature dataset:MockDatasetClassification/0/?, n_splits:int/0/int, seed:int/0/int, train_size:float/0/float · returned list · level recorded 2026-09-25
list_images_in_dir utils/dataset_utils.py ran MIT (permissive) · 3c50560fdbf5c682 · report fixture: signature path:str/0/str · returned list · level recorded 2026-09-25
np2torch utils/base.py ran MIT (permissive) · 559c59239df0058f · report fixture: signature nparray:ndarray/4/float · returned Tensor · level recorded 2026-09-25
raw2rgb processing/pipeline_torch.py ran MIT (permissive) · c5742d0c1047c423 · report fixture: signature raw:Tensor/3/float, black_level:list/1/int, reduce_size:bool/0/bool, out_channels:int/0/int · returned Tensor · level recorded 2026-09-25
read_label_csv dataset.py ran MIT (permissive) · 95281f5c74968285 · report fixture: signature df:DataFrame/0/? · returned tuple · level recorded 2026-09-25
read_label_file in 8 papers dataset.py ran MIT (permissive) · 045190de81281aa8 · report fixture: signature label_file_path:str/0/str · returned tuple · level recorded 2026-09-25
remove_blacklv processing/pipeline_numpy.py ran fingerprinted MIT (permissive) · fe707df7a8e80910 · report fixture: signature rawImg:Tensor/2/float, black_level:Tensor/1/float · returned Tensor · level recorded 2026-09-25
resnet_model model.py ran MIT (permissive) · c3c598b1b4b67b24 · report fixture: signature model:str/0/str, pretrained:bool/0/bool, in_channels:int/0/int, fc_out_features:int/0/int · returned ResNet · level recorded 2026-09-25
ssim in 112 papers utils/ssim.py ran · our draft was wrong fingerprinted MIT (permissive) · 9151c793f90473f0 · report fixture: signature img1:Tensor/4/float, img2:Tensor/4/float, window_size:int/0/int, size_average:bool/0/bool · returned Tensor · level recorded 2026-09-26
str2bool in 533 papers utils/base.py ran MIT (permissive) · d19549ae909a3ef9 · report fixture: signature string:str/0/str · returned bool · level recorded 2026-09-25
torch2np in 5 papers utils/base.py ran fingerprinted MIT (permissive) · 247a4dfe7a43e089 · report fixture: signature torchtensor:Tensor/4/float · returned ndarray · level recorded 2026-09-25
plasma_fractal in 12 papers utils/hendrycks_robustness.py unverified MIT (permissive) · cb4092b5e3cb3af3 · report

Tasks

Model Selection

Datasets

Introduced by this paper, per the archive.

Raw-Microscopy and Raw-Drone

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

SPEEDTest

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections